In [1]:

    

import pandas as pd
from pandas import DataFrame

import census
import settings
import us

from itertools import islice

# instantiate the census object

c=census.Census(settings.CENSUS_KEY)


    

In [2]:

    

def places(variables="NAME"):
    
    for state in us.states.STATES:
        print state
        geo = {'for':'place:*', 'in':'state:{s_fips}'.format(s_fips=state.fips)}
        for place in c.sf1.get(variables, geo=geo):
            yield place


    

In [3]:

    

r = list(islice(places("NAME,P0010001"), None))
places_df = DataFrame(r)
places_df.P0010001 = places_df.P0010001.astype('int')

places_df['FIPS'] = places_df.apply(lambda s: s['state']+s['place'], axis=1)

print "number of places", len(places_df)
print "total pop", places_df.P0010001.sum()
places_df.head()


    

    




Alabama
Alaska
Arizona
Arkansas
California
Colorado
Connecticut
Delaware
District of Columbia
Florida
Georgia
Hawaii
Idaho
Illinois
Indiana
Iowa
Kansas
Kentucky
Louisiana
Maine
Maryland
Massachusetts
Michigan
Minnesota
Mississippi
Missouri
Montana
Nebraska
Nevada
New Hampshire
New Jersey
New Mexico
New York
North Carolina
North Dakota
Ohio
Oklahoma
Oregon
Pennsylvania
Rhode Island
South Carolina
South Dakota
Tennessee
Texas
Utah
Vermont
Virginia
Washington
West Virginia
Wisconsin
Wyoming
number of places 29261
total pop 228457238






    
Out[3]:






  

    

      

      
NAME
      
P0010001
      
place
      
state
      
FIPS
    
  
  

    

      
0
      
      Abanda CDP
      
  192
      
 00100
      
 01
      
 0100100
    
    

      
1
      
  Abbeville city
      
 2688
      
 00124
      
 01
      
 0100124
    
    

      
2
      
 Adamsville city
      
 4522
      
 00460
      
 01
      
 0100460
    
    

      
3
      
    Addison town
      
  758
      
 00484
      
 01
      
 0100484
    
    

      
4
      
      Akron town
      
  356
      
 00676
      
 01
      
 0100676
    
  

In [4]:

    

assert places_df.P0010001.sum() == 228457238
# number of places in 2010 Census
assert len(places_df) == 29261


    

In [ ]: